datachain 0.37.4__py3-none-any.whl → 0.37.6__py3-none-any.whl

datachain/query/dataset.py

@@ -426,8 +426,10 @@ class UDFStep(Step, ABC):
         """Method that creates a table where temp udf results will be saved"""
 
     def process_input_query(self, query: Select) -> tuple[Select, list["Table"]]:
-        """Apply any necessary processing to the input query"""
-        return query, []
+        """Materialize inputs, ensure sys columns are available, needed for checkpoints,
+        needed for map to work (merge results)"""
+        table = self.catalog.warehouse.create_pre_udf_table(query)
+        return sqlalchemy.select(*table.c), [table]
 
     @abstractmethod
     def create_result_query(
@@ -628,23 +630,18 @@ class UDFStep(Step, ABC):
     def apply(
         self, query_generator: QueryGenerator, temp_tables: list[str]
     ) -> "StepResult":
-        _query = query = query_generator.select()
+        query, tables = self.process_input_query(query_generator.select())
+        _query = query
 
         # Apply partitioning if needed.
         if self.partition_by is not None:
-            _query = query = self.catalog.warehouse._regenerate_system_columns(
-                query_generator.select(),
-                keep_existing_columns=True,
-                regenerate_columns=["sys__id"],
-            )
             partition_tbl = self.create_partitions_table(query)
-            temp_tables.append(partition_tbl.name)
             query = query.outerjoin(
                 partition_tbl,
                 partition_tbl.c.sys__id == query.selected_columns.sys__id,
             ).add_columns(*partition_columns())
+            tables = [*tables, partition_tbl]
 
-        query, tables = self.process_input_query(query)
         temp_tables.extend(t.name for t in tables)
         udf_table = self.create_udf_table(_query)
         temp_tables.append(udf_table.name)
@@ -675,13 +672,6 @@ class UDFSignal(UDFStep):
 
         return self.catalog.warehouse.create_udf_table(udf_output_columns)
 
-    def process_input_query(self, query: Select) -> tuple[Select, list["Table"]]:
-        if os.getenv("DATACHAIN_DISABLE_QUERY_CACHE", "") not in ("", "0"):
-            return query, []
-        table = self.catalog.warehouse.create_pre_udf_table(query)
-        q: Select = sqlalchemy.select(*table.c)
-        return q, [table]
-
     def create_result_query(
         self, udf_table, query
     ) -> tuple[QueryGeneratorFunc, list["sqlalchemy.Column"]]:

{datachain-0.37.4.dist-info → datachain-0.37.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.37.4
+Version: 0.37.6
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.37.4.dist-info → datachain-0.37.6.dist-info}/RECORD

@@ -132,7 +132,7 @@ datachain/model/ultralytics/pose.py,sha256=pvoXrWWUSWT_UBaMwUb5MBHAY57Co2HFDPigF
 datachain/model/ultralytics/segment.py,sha256=v9_xDxd5zw_I8rXsbl7yQXgEdTs2T38zyY_Y4XGN8ok,3194
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=ugTlSFqh_kxMcG6vJ5XrEzG9jBXRdb7KRAEEsFWiPew,4190
-datachain/query/dataset.py,sha256=vYSbtpVaobIC7uCWdx-wgPOh9_T8oRQoVw1ZC_9ArKE,67527
+datachain/query/dataset.py,sha256=kfNh6B6pYSz3batUpwW_6vJ7XRLwLfC08hKOZUMjf3o,67126
 datachain/query/dispatch.py,sha256=Tg73zB6vDnYYYAvtlS9l7BI3sI1EfRCbDjiasvNxz2s,16385
 datachain/query/metrics.py,sha256=qOMHiYPTMtVs2zI-mUSy8OPAVwrg4oJtVF85B9tdQyM,810
 datachain/query/params.py,sha256=JkVz6IKUIpF58JZRkUXFT8DAHX2yfaULbhVaGmHKFLc,826
@@ -165,9 +165,9 @@ datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=xQzzmvQRKsPteDKbpgOxd4r971BnFaK33mcOl0FuGeI,2883
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.37.4.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.37.4.dist-info/METADATA,sha256=00fv6-Lg7pJ2yBxYEaRtnMDF4C_Y5SUp5tsPwS8hUXk,13762
-datachain-0.37.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.37.4.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.37.4.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.37.4.dist-info/RECORD,,
+datachain-0.37.6.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.37.6.dist-info/METADATA,sha256=zBPCt_CUJzcP3rNzpykwH9v9A388r273Huo6Hp_f0Jk,13762
+datachain-0.37.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.37.6.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.37.6.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.37.6.dist-info/RECORD,,